INDEX

Explanations

references to specific video game titles and characters, particularly from the Metal Gear Solid series

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

elong

-0.89

 eleph

-0.79

headed

-0.71

housing

-0.71

umbn

-0.70

uckland

-0.69

nah

-0.69

rist

-0.69

 ende

-0.68

onyms

-0.67

POSITIVE LOGITS

 Trilogy

1.19

 Chronicles

1.18

 Reborn

1.16

âĦ¢:

1.15

 sequel

1.08

 Origins

1.08

 Remastered

1.08

 Generations

1.07

 Legends

1.05

RPG

1.03

Activations Density 0.911%

references to specific video game titles and characters, particularly from the Metal Gear Solid series

No Comments

No Known Activations